Reading Tumor Ecosystems from Routine Histology
Researchers introduce CANVAS, an AI framework for translating hematoxylin and eosin images into spatial maps of tumor habitats.
Li et al. introduce CANVAS, an AI framework for translating hematoxylin and eosin images into spatial maps of tumor habitats. CANVAS extends habitat mapping to archival pathology samples, suggesting a path toward more accessible precision oncology. Tumors are complex ecosystems comprising a multitude of interdependent cell populations. By measuring proteins and transcripts in situ using multiplex spatial proteomics and transcriptomics, researchers have characterized the spatial organization of tumors across a wide range of cancers, revealing recurrent cellular neighborhoods associated with disease progression and clinical outcomes.
The high cost and technical complexity of these technologies have confined them to a research setting, impeding their adoption in routine clinical practice. The potential of spatially resolved molecular profiling to inform diagnosis, prognosis, and treatment decisions remains largely untapped.
This paper presents a significant advancement in the field, enabling the analysis of tumor ecosystems from routine histology.